
Query multi-source AppSec catalogs (CWE / OWASP Cheat Sheet Series / GitHub Advisory Database / AppSec.fyi) for a given security finding and propose a synthesis row to the security-field-notes synthesis-ledger via PR. Use when a producer skill (sec-audit-static, sec-audit-dast, external-software-analysis) emits a finding that needs external reference enrichment, or when packaging an assessment finding for downstream remediation context.
# security-testing-as-code: Assessment as Executable Project Transform security assessment deliverables from static documents into version-controlled, executable projects. Findings become reproducible code; evidence becomes artifacts; knowledge becomes inheritable structure. ## Core Thesis > "A diagnosis is a document" is the fundamental flaw. A diagnosis should be a project. Traditional security reports (Word, Excel, portal entries) produce ephemeral knowledge that dies upon publication. Th
Security architecture review for codebases, producing Data Flow Diagram (DFD) with trust boundaries, Attack Flow overlay, scoped attack surface inventory, sensitive data map, and risk summary grounded in code. Use when asked to perform architecture-focused security review, reconstruct security design from code, or produce DFD/attack-flow documentation.
# sec-cluster: Security Code Clustering Dataflow-based code clustering for security assessments. Groups (Endpoint, Sink) paths by shared review strategy, enabling representative-sample review instead of exhaustive per-path analysis. ## Core Principle > A cluster does not guarantee identical results. A cluster provides the possibility of applying the same review strategy. Therefore the operating procedure is: **verify clusters while using them**, not trust them blindly. ## When to Use - Cod
DAST/ASM workflow for external asset discovery, probing, and scanning with SARIF output. Use for runtime/endpoint-based assessments and asset management scanning.
Static code security audit playbook (SAST, SCA, secret detection) with standardized JSON outputs and reporting. Use for source-code based assessments, schema validation, and generating final reports.
External software analysis workflows for binaries/packages (decompilation, reverse engineering, static analysis, fuzzing, and evidence collection). Use when analyzing third-party software without source access.
DAST/ASM workflow for external asset discovery, probing, and scanning with SARIF output. Use for runtime/endpoint-based assessments and asset management scanning.
External software analysis workflows for binaries/packages (decompilation, reverse engineering, static analysis, fuzzing, and evidence collection). Use when analyzing third-party software without source access.
Dataflow-based code clustering for security assessments. Groups (Endpoint, Sink) paths by shared review strategy so reviewers sample representative cases instead of exhaustively reviewing every path. Use when scoping manual review on a codebase with 50+ endpoints, repetitive sanitization patterns, or after initial SAST/SCA produces large finding sets that need triage.
Security architecture review for codebases, producing Data Flow Diagram (DFD) with trust boundaries, Attack Flow overlay, scoped attack surface inventory, sensitive data map, and risk summary grounded in code. Use when asked to perform architecture-focused security review, reconstruct security design from code, or produce DFD/attack-flow documentation.
Static code security audit playbook (SAST, SCA, secret detection) with standardized JSON outputs and reporting. Use for source-code based assessments, schema validation, and generating final reports.
Transform security assessment deliverables from static documents (Word/Excel/portal) into version-controlled, executable projects. PoCs replace narrative claims; saved HTTP requests replace checkboxes; commit hashes enable exact-state reproduction. Use when scoping methodology for an audit, when an existing assessment needs to be made reproducible, or when assessment outputs must be inheritable across teams.